Back to directory

Helix

A self-hosted platform that runs a fleet of coding agents, each in its own GPU-accelerated sandbox desktop, coordinated through a spec-driven Kanban board so a team can review and merge their pull requests.

Helix

Helix runs coding agents on shared infrastructure instead of a developer's own laptop, giving each agent its own isolated sandbox with a full desktop: browser, terminal, filesystem and GUI applications. Work is organized in projects, each with a Kanban board where tasks move from backlog through planning, spec review, in-progress work and a pull request to merged.

A task starts as a short description of the desired outcome. A planning agent reads the connected repository and writes a specification to a branch for the team to review and revise; once approved, an implementation agent codes the change live in its sandbox, and a team member can watch, steer it, or switch to a different agent mid-session before a pull request is opened in the real repository.

It works with existing agent harnesses such as Claude Code, Codex, Gemini CLI, Qwen Code or other ACP-compatible agents, against self-hosted or hosted model providers, and can run fully self-hosted, including air-gapped.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.